Application of Radial Basis Network Model for HIV/AIDs Regimen Specifications

TL;DR

This paper presents a radial basis function neural network model designed to predict patient survival times based on HIV/AIDS regimen data, trained on patient records to assist in treatment planning.

Contribution

It introduces a neural network approach specifically tailored for HIV/AIDS regimen prediction, utilizing MATLAB for implementation and testing on real patient data.

Findings

Model trained on 300 patients' data

Tested on 100 patients' data

Demonstrates potential for aiding treatment decisions

Abstract

HIV/AIDs Regimen specification one of many problems for which bioinformaticians have implemented and trained machine learning methods such as neural networks. Predicting HIV resistance would be much easier, but unfortunately we rarely have enough structural information available to train a neural network. To network model designed to predict how long the HIV patient can prolong his/her life time with certain regimen specification. To learn this model 300 patient's details have taken as a training set to train the network and 100 patients medical history has taken to test this model. This network model is trained using MAT lab implementation.